© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 16141
    Prev
    Next
    INDEX
    Explanations

    the word "immediate."

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate urgency or prompt action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conduct
    -0.77
    cius
    -0.74
    ifling
    -0.74
    nan
    -0.74
    midt
    -0.69
    acus
    -0.68
    ingers
    -0.68
    glers
    -0.68
    missions
    -0.68
    doctor
    -0.66
    POSITIVE LOGITS
    aneously
    1.19
     gratification
    1.15
     immediate
    0.96
     aftermath
    0.90
     reaction
    0.84
     immedi
    0.83
     overflow
    0.78
     consequence
    0.77
     response
    0.74
     outcry
    0.73
    Activations Density 0.008%

    No Known Activations